Text Generation
Transformers
Safetensors
French
fiscalité
génération-de-texte
français
8-bit precision
Instructions to use Aktraiser/modele-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aktraiser/modele-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Aktraiser/modele-test")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Aktraiser/modele-test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Aktraiser/modele-test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Aktraiser/modele-test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aktraiser/modele-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Aktraiser/modele-test
- SGLang
How to use Aktraiser/modele-test with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Aktraiser/modele-test" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aktraiser/modele-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Aktraiser/modele-test" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aktraiser/modele-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Aktraiser/modele-test with Docker Model Runner:
docker model run hf.co/Aktraiser/modele-test
Update handler.py
Browse files- handler.py +28 -27
handler.py
CHANGED
|
@@ -16,35 +16,36 @@ class EndpointHandler:
|
|
| 16 |
self.model, self.tokenizer = load_model(path)
|
| 17 |
self.pipeline = TextGenerationPipeline(
|
| 18 |
model=self.model,
|
| 19 |
-
tokenizer=self.tokenizer
|
| 20 |
-
max_new_tokens=512,
|
| 21 |
-
temperature=0.7,
|
| 22 |
-
top_p=0.95,
|
| 23 |
-
repetition_penalty=1.15,
|
| 24 |
-
do_sample=True
|
| 25 |
)
|
| 26 |
|
| 27 |
def __call__(self, data):
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
}
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
return {"
|
| 50 |
-
return [{"generated_text": o["generated_text"]} for o in outputs]
|
|
|
|
| 16 |
self.model, self.tokenizer = load_model(path)
|
| 17 |
self.pipeline = TextGenerationPipeline(
|
| 18 |
model=self.model,
|
| 19 |
+
tokenizer=self.tokenizer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
)
|
| 21 |
|
| 22 |
def __call__(self, data):
|
| 23 |
+
# Extraire le texte d'entrée
|
| 24 |
+
if isinstance(data, dict):
|
| 25 |
+
text = data.pop("inputs", "")
|
| 26 |
+
else:
|
| 27 |
+
text = data
|
| 28 |
+
|
| 29 |
+
# Paramètres de génération
|
| 30 |
+
params = {
|
| 31 |
+
"max_new_tokens": data.get("max_new_tokens", 512),
|
| 32 |
+
"temperature": data.get("temperature", 0.7),
|
| 33 |
+
"top_p": data.get("top_p", 0.95),
|
| 34 |
+
"repetition_penalty": data.get("repetition_penalty", 1.15),
|
| 35 |
+
"do_sample": data.get("do_sample", True)
|
| 36 |
}
|
| 37 |
+
|
| 38 |
+
try:
|
| 39 |
+
# Générer le texte
|
| 40 |
+
result = self.pipeline(
|
| 41 |
+
text,
|
| 42 |
+
**params
|
| 43 |
+
)
|
| 44 |
|
| 45 |
+
# Formater la sortie
|
| 46 |
+
if isinstance(result, list):
|
| 47 |
+
return {"generated_text": result[0]["generated_text"]}
|
| 48 |
+
return {"generated_text": result["generated_text"]}
|
| 49 |
+
|
| 50 |
+
except Exception as e:
|
| 51 |
+
return {"error": str(e)}
|
|
|